Saved in:
Bibliographic Details
Main Authors: Park, Giseung, Sung, Youngchul
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.20957
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916635203338240
author Park, Giseung
Sung, Youngchul
author_facet Park, Giseung
Sung, Youngchul
contents In this paper, we introduce a simple yet effective reward dimension reduction method to tackle the scalability challenges of multi-objective reinforcement learning algorithms. While most existing approaches focus on optimizing two to four objectives, their abilities to scale to environments with more objectives remain uncertain. Our method uses a dimension reduction approach to enhance learning efficiency and policy performance in multi-objective settings. While most traditional dimension reduction methods are designed for static datasets, our approach is tailored for online learning and preserves Pareto-optimality after transformation. We propose a new training and evaluation framework for reward dimension reduction in multi-objective reinforcement learning and demonstrate the superiority of our method in environments including one with sixteen objectives, significantly outperforming existing online dimension reduction methods.
format Preprint
id arxiv_https___arxiv_org_abs_2502_20957
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reward Dimension Reduction for Scalable Multi-Objective Reinforcement Learning
Park, Giseung
Sung, Youngchul
Machine Learning
In this paper, we introduce a simple yet effective reward dimension reduction method to tackle the scalability challenges of multi-objective reinforcement learning algorithms. While most existing approaches focus on optimizing two to four objectives, their abilities to scale to environments with more objectives remain uncertain. Our method uses a dimension reduction approach to enhance learning efficiency and policy performance in multi-objective settings. While most traditional dimension reduction methods are designed for static datasets, our approach is tailored for online learning and preserves Pareto-optimality after transformation. We propose a new training and evaluation framework for reward dimension reduction in multi-objective reinforcement learning and demonstrate the superiority of our method in environments including one with sixteen objectives, significantly outperforming existing online dimension reduction methods.
title Reward Dimension Reduction for Scalable Multi-Objective Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2502.20957